Research map / Label-efficient and robust learning / Noisy labels
USDNL: Uncertainty-Based Single Dropout in Noisy Label Learning
Yuanzhuo Xu, Xiaoguang Niu, Jie Yang, Steve Drew, Jiayu Zhou, Ruizhi Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use single-dropout sample selection instead of the strongest listed baseline | USDNL · MNIST with CCN noise | accuracy (%) | Improved |
| Use single-dropout sample selection instead of the strongest listed baseline | USDNL · CIFAR-10 with CCN noise | accuracy (%) | Improved |
| Use single-dropout sample selection instead of the strongest listed baseline | USDNL · CIFAR-100 with CCN noise | accuracy (%) | Improved |
| Use single-dropout sample selection instead of the strongest listed baseline | USDNL · CIFAR-80N-O | accuracy (%) | Mixed |
| Use single-dropout sample selection instead of the strongest listed baseline | USDNL · CIFAR-10 IDN | accuracy (%) | Improved |
| Use single-dropout sample selection instead of the strongest listed baseline | USDNL · CIFAR-100 IDN | accuracy (%) | Improved |
| Use USDNL rather than JoSRC | USDNL with ResNet-18 · Clothing1M | accuracy (%): 70.69 -> 71.74 | Improved |
| Remove dropout from USDNL (ablation) | USDNL · CIFAR-10 Sym-50% | accuracy (%) | Hurt |
| Use one dropout sampling rather than multiple dropout samplings (ablation) | USDNL · CIFAR-10 Sym-50% | accuracy (%) | No clear effect |
| Use USDNL rather than Standard | 9-CNN training · IDN-CIFAR-10 Sym-50% (reported complexity comparison) | training time (second/epoch): 29.1±0.7 -> 32.3±0.1 | Improved |
Later papers that compared with this method
1 later accepted paper reports USDNL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Variational Rectification Inference for Learning with Noisy Labels (IJCV 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- JoSRC — Jo-SRC: A Contrastive Approach for Combating Noisy Labels (CVPR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Uncertainty-Aware Learning against Label Noise on Imbalanced Datasets (AAAI 2022 · similarity 0.89)
- Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model (AAAI 2021 · similarity 0.88)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.88)
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization (NeurIPS 2025 · similarity 0.88)
- $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise (NeurIPS 2024 · similarity 0.87)
- Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
